《计算机应用研究》|Application Research of Computers

基于CNN-WaveNet的滚动轴承剩余寿命预测

Remaining life prediction of rolling bearing based on CNN-WaveNet

免费全文下载 (已被下载 次)  
获取PDF全文
作者 全航,张强,邵思羽,牛天林,杨新宇
机构 空军工程大学 a.研究生学院;b.防空反导学院,西安 710051
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)10-038-3098-06
DOI 10.19734/j.issn.1001-3695.2021.03.0078
摘要 为保证设备正常运行并准确预测轴承剩余寿命,提出二维卷积神经网络与改进WaveNet组合的寿命预测模型。为克服未优化的递归网络在预测训练过程中易出现梯度消失问题,该模型引入了WaveNet时序网络结构。针对原始WaveNet结构不适用滚动轴承振动数据情况,将WaveNet结构改进与二维卷积神经网络结合应用于滚动轴承寿命预测。模型利用二维卷积网络提取一维振动序列的特征,随后特征输入WaveNet并进行滚动轴承的预测寿命。改进模型相比于深度循环网络计算效率更高、结果更准确,相比于原始CNN-WaveNet-O模型预测结果更准确。相比于深度长短期记忆网络模型,改进方法预测结果均方根误差降低了11.04%,评分函数降低了11.34%。
关键词 深度学习; 卷积神经网络; WaveNet网络; 滚动轴承; 寿命预测
基金项目 陕西省自然科学基础研究计划资助项目
本文URL http://www.arocmag.com/article/01-2021-10-038.html
英文标题 Remaining life prediction of rolling bearing based on CNN-WaveNet
作者英文名 Quan Hang, Zhang Qiang, Shao Siyu, Niu Tianlin, Yang Xinyu
机构英文名 a.Graduate School,b.Air Defense & Antimissile School,Air Force Engineering University,Xi'an 710051,China
英文摘要 In order to ensure the normal operation of the equipment and to predict the remaining life of the bearing, this paper proposed a life prediction model based on the combination of two-dimensional convolutional neural network and an improved WaveNet. To overcome the gradient vanishing problem of the unoptimized recurrent networks in the process of prediction training, the WaveNet time-series networks structure was introduced into the model. Aiming at the situation that the original WaveNet structure was not suitable for rolling bearing vibration data, the improved WaveNet structure combined with two-dimensionalconvolutional neural networks was applied to the life prediction of rolling bearing. The model extracted the features of one-dimensional vibration sequence using two-dimensional convolutional networks, and then input the features to the WaveNet to predict the remaining life of the rolling bearing. Compared with the deep recurrent networks, the combined model has higher computational efficiency and more accurate results. Compared with the CNN-WaveNet-O model, the improved model has more accurate prediction results. Compared with the deep long short-term memory networks model, the root mean square error of the prediction results of this model is reduced by 11.04%, and the scoring function of the prediction results is reduced by 11.34%.
英文关键词 deep learning; convolutional neural networks(CNN); WaveNet; rolling bearing; life prediction
参考文献 查看稿件参考文献
 
收稿日期 2021/3/9
修回日期 2021/5/3
页码 3098-3103
中图分类号 TP183
文献标志码 A